chaiml-1107-quang-ir-mi_97338

developer_uid: chai_backend_admin

submission_id: chaiml-1107-quang-ir-mi_97338_v1

model_name: training123

model_group: ChaiML/1107-quang-ir-mix

status: torndown

timestamp: 2025-11-11T08:21:33+00:00

num_battles: 5454

num_wins: 2637

celo_rating: 1299.11

family_friendly_score: 0.5369999999999999

family_friendly_standard_error: 0.007051680650738517

submission_type: basic

model_repo: ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_multsth25k_0164641ep_2e6ct

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.3812329214531063, 'latency_mean': 2.6229684352874756, 'latency_p50': 2.609537124633789, 'latency_p90': 2.9004568338394163}, {'batch_size': 2, 'throughput': 0.5745989582429308, 'latency_mean': 3.4725899016857147, 'latency_p50': 3.4654042720794678, 'latency_p90': 3.805692434310913}, {'batch_size': 3, 'throughput': 0.7069828033933561, 'latency_mean': 4.228583705425263, 'latency_p50': 4.217987060546875, 'latency_p90': 4.594308137893677}, {'batch_size': 4, 'throughput': 0.8068460864581839, 'latency_mean': 4.9370694875717165, 'latency_p50': 4.947664141654968, 'latency_p90': 5.573455357551574}, {'batch_size': 5, 'throughput': 0.8643549973211574, 'latency_mean': 5.756844625473023, 'latency_p50': 5.758354902267456, 'latency_p90': 6.5762203454971315}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_multsth25k_0164641ep_2e6ct

model_size: 24B

ranking_group: single

throughput_3p7s: 0.62

us_pacific_date: 2025-11-08

win_ratio: 0.4834983498349835

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', 'You:', '####'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\n{bot_name}:', 'truncate_by_message': True}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-1107-quang-ir-mi-97338-v1-mkmlizer
Waiting for job on chaiml-1107-quang-ir-mi-97338-v1-mkmlizer to finish
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ║                                                                     ║
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: Downloaded to shared memory in 57.971s
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: Checking if ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_multsth25k_0164641ep_2e6ct already exists in ChaiML
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpvbjlst3u, device:0
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: quantized model in 42.602s
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: Processed model ChaiML/1107-quang-ir-mixall-cld-i8a6-dpohrd-f5000-dpo_multsth25k_0164641ep_2e6ct in 100.573s
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-97338-v1/nvidia
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-97338-v1/nvidia/config.json
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-97338-v1/nvidia/special_tokens_map.json
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-97338-v1/nvidia/tokenizer_config.json
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-97338-v1/nvidia/tokenizer.json
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-97338-v1/nvidia/flywheel_model.1.safetensors
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-1107-quang-ir-mi-97338-v1/nvidia/flywheel_model.0.safetensors
chaiml-1107-quang-ir-mi-97338-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:15, 22.94it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:08, 39.01it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:08, 41.71it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:10, 32.31it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:07, 44.44it/s]
Loading 0:  10%|█         | 38/363 [00:01<00:10, 30.76it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:12, 26.38it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 28.29it/s]
Loading 0:  14%|█▍        | 50/363 [00:01<00:13, 22.69it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:12, 24.22it/s]
Loading 0:  16%|█▌        | 58/363 [00:02<00:13, 22.96it/s]
Loading 0:  17%|█▋        | 61/363 [00:02<00:15, 19.32it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:15, 18.98it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 23.51it/s]
Loading 0:  20%|█▉        | 72/363 [00:02<00:14, 19.97it/s]
Loading 0:  21%|██        | 75/363 [00:02<00:13, 21.46it/s]
Loading 0:  22%|██▏       | 79/363 [00:03<00:11, 25.06it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 25.42it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:09, 28.87it/s]
Loading 0:  25%|██▍       | 90/363 [00:03<00:09, 28.67it/s]
Loading 0:  26%|██▌       | 94/363 [00:03<00:09, 27.82it/s]
Loading 0:  27%|██▋       | 99/363 [00:03<00:08, 32.06it/s]
Loading 0:  28%|██▊       | 103/363 [00:03<00:08, 30.84it/s]
Loading 0:  29%|██▉       | 107/363 [00:04<00:09, 25.91it/s]
Loading 0:  31%|███       | 112/363 [00:04<00:08, 28.87it/s]
Loading 0:  32%|███▏      | 116/363 [00:04<00:08, 30.04it/s]
Loading 0:  33%|███▎      | 120/363 [00:04<00:07, 32.30it/s]
Loading 0:  34%|███▍      | 124/363 [00:04<00:07, 30.37it/s]
Loading 0:  36%|███▌      | 129/363 [00:04<00:06, 33.92it/s]
Loading 0:  37%|███▋      | 133/363 [00:04<00:08, 27.15it/s]
Loading 0:  38%|███▊      | 138/363 [00:05<00:08, 26.27it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:08, 24.77it/s]
Loading 0:  41%|████      | 149/363 [00:05<00:06, 33.90it/s]
Loading 0:  42%|████▏     | 153/363 [00:05<00:08, 23.74it/s]
Loading 0:  44%|████▎     | 158/363 [00:05<00:08, 24.48it/s]
Loading 0:  45%|████▌     | 165/363 [00:05<00:06, 31.30it/s]
Loading 0:  47%|████▋     | 169/363 [00:06<00:06, 30.43it/s]
Loading 0:  48%|████▊     | 174/363 [00:06<00:05, 33.33it/s]
Loading 0:  49%|████▉     | 178/363 [00:06<00:05, 31.76it/s]
Loading 0:  50%|█████     | 182/363 [00:06<00:05, 32.82it/s]
Loading 0:  52%|█████▏    | 187/363 [00:06<00:05, 29.75it/s]
Loading 0:  53%|█████▎    | 191/363 [00:06<00:05, 29.03it/s]
Loading 0:  54%|█████▎    | 195/363 [00:07<00:06, 26.03it/s]
Loading 0:  55%|█████▌    | 201/363 [00:19<02:13,  1.21it/s]
Loading 0:  56%|█████▌    | 203/363 [00:20<01:54,  1.40it/s]
Loading 0:  57%|█████▋    | 208/363 [00:20<01:13,  2.11it/s]
Loading 0:  58%|█████▊    | 211/363 [00:20<00:56,  2.67it/s]
Loading 0:  59%|█████▉    | 215/363 [00:20<00:39,  3.72it/s]
Loading 0:  60%|██████    | 219/363 [00:20<00:29,  4.96it/s]
Loading 0:  62%|██████▏   | 224/363 [00:20<00:20,  6.91it/s]
Loading 0:  63%|██████▎   | 229/363 [00:21<00:14,  9.52it/s]
Loading 0:  64%|██████▍   | 232/363 [00:21<00:11, 11.14it/s]
Loading 0:  65%|██████▌   | 237/363 [00:21<00:08, 15.10it/s]
Loading 0:  66%|██████▋   | 241/363 [00:21<00:07, 17.15it/s]
Loading 0:  68%|██████▊   | 246/363 [00:21<00:05, 21.57it/s]
Loading 0:  69%|██████▉   | 250/363 [00:21<00:04, 23.01it/s]
Loading 0:  70%|███████   | 255/363 [00:21<00:04, 26.83it/s]
Loading 0:  71%|███████▏  | 259/363 [00:21<00:03, 26.72it/s]
Loading 0:  73%|███████▎  | 266/363 [00:22<00:02, 33.97it/s]
Loading 0:  74%|███████▍  | 270/363 [00:22<00:03, 23.59it/s]
Loading 0:  76%|███████▌  | 275/363 [00:22<00:03, 23.89it/s]
Loading 0:  78%|███████▊  | 282/363 [00:22<00:02, 30.95it/s]
Loading 0:  79%|███████▉  | 286/363 [00:22<00:02, 30.08it/s]
Loading 0:  80%|████████  | 291/363 [00:22<00:02, 33.29it/s]
Loading 0:  81%|████████▏ | 295/363 [00:23<00:02, 31.25it/s]
Loading 0:  82%|████████▏ | 299/363 [00:23<00:01, 32.31it/s]
Loading 0:  84%|████████▎ | 304/363 [00:23<00:02, 28.83it/s]
Loading 0:  85%|████████▍ | 308/363 [00:23<00:01, 28.31it/s]
Loading 0:  86%|████████▌ | 312/363 [00:23<00:02, 25.47it/s]
Loading 0:  88%|████████▊ | 318/363 [00:23<00:01, 31.33it/s]
Loading 0:  89%|████████▊ | 322/363 [00:24<00:01, 30.19it/s]
Loading 0:  90%|█████████ | 327/363 [00:24<00:01, 33.71it/s]
Loading 0:  91%|█████████ | 331/363 [00:24<00:01, 29.90it/s]
Loading 0:  92%|█████████▏| 335/363 [00:24<00:00, 31.48it/s]
Loading 0:  93%|█████████▎| 339/363 [00:24<00:00, 31.83it/s]
Loading 0:  94%|█████████▍| 343/363 [00:24<00:01, 19.88it/s]
Loading 0:  96%|█████████▌| 348/363 [00:25<00:00, 21.56it/s]
Loading 0:  98%|█████████▊| 355/363 [00:25<00:00, 28.97it/s]
Loading 0:  99%|█████████▉| 359/363 [00:25<00:00, 28.42it/s]
                                                            
Job chaiml-1107-quang-ir-mi-97338-v1-mkmlizer completed after 175.39s with status: succeeded
Stopping job with name chaiml-1107-quang-ir-mi-97338-v1-mkmlizer
Pipeline stage MKMLizer completed in 176.05s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.50s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-1107-quang-ir-mi-97338-v1
Waiting for inference service chaiml-1107-quang-ir-mi-97338-v1 to be ready
Inference service chaiml-1107-quang-ir-mi-97338-v1 ready after 170.6073236465454s
Pipeline stage MKMLDeployer completed in 171.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4747350215911865s
Received healthy response to inference request in 2.140047073364258s
Received healthy response to inference request in 2.183724880218506s
Received healthy response to inference request in 2.1446311473846436s
Received healthy response to inference request in 2.1933109760284424s
5 requests
0 failed requests
5th percentile: 2.140963888168335
10th percentile: 2.1418807029724123
20th percentile: 2.1437143325805663
30th percentile: 2.152449893951416
40th percentile: 2.168087387084961
50th percentile: 2.183724880218506
60th percentile: 2.1875593185424806
70th percentile: 2.191393756866455
80th percentile: 2.249595785140991
90th percentile: 2.362165403366089
95th percentile: 2.418450212478638
99th percentile: 2.463478059768677
mean time: 2.227289819717407
Pipeline stage StressChecker completed in 12.84s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.66s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.64s
Shutdown handler de-registered
chaiml-1107-quang-ir-mi_97338_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-1107-quang-ir-mi-97338-v1-profiler
Waiting for inference service chaiml-1107-quang-ir-mi-97338-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2986.67s
Shutdown handler de-registered
chaiml-1107-quang-ir-mi_97338_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-1107-quang-ir-mi_97338_v1 status is now torndown due to DeploymentManager action